Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

add_mist

Lay a mist band across an Aseprite scene at a specified row and thickness, controlling density, drift, color, and sunlit warmth on a new layer.

Instructions

Lay a band of mist across the scene, centred on row y and thickness rows deep: along a far shore, in a valley, over a marsh. It is thickest along its middle and breaks up toward its edges, in a few see-through strengths of color; density (0-1) is how much of the band it fills. drift is how many pixels it travels over the sprite's frames (negative for leftward; try 1 a frame), as a seamless loop. Near sun_x the mist takes on warm, as low sun lights it. It goes on a new layer named layer, just above the layer named above (the water, say, to keep it behind a foreground), or on top. One undo step. Headless: pass file.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "y": "<y>"
    },
    "name": "add_mist"
  }
}

Input Schema

NameRequiredDescriptionDefault
yYes
fileNo
seedNo
warmNo#ffd9a0
aboveNo
colorNo#9a86c0
driftNo
layerNoMist
sun_xNo
densityNo
thicknessNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.3/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations supply only a title, so the description carries the behavioral burden and does so well: it discloses the undo cost ('One undo step'), the layer insertion semantics (new layer just above `above`, or on top), and the headless requirement ('pass `file`'). It omits whether creation fails if the `above` layer is missing, which is the main remaining gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The most important facts (action, geometry, placement, undo cost) are front-loaded, and most sentences do double duty by explaining a parameter alongside its visual effect. It is dense but readable; a couple of clauses about aesthetic appearance could be trimmed without losing invocation-relevant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter mutation tool with no annotations and no output schema, the description covers placement, loop behavior, undo cost, and headless mode. An agent has everything needed to invoke it correctly apart from the meaning of `seed`.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage across 11 parameters, the description must compensate and largely does: it defines y, thickness, color, density (explicitly 0-1), drift (pixels per frame, negative = leftward, suggested value), sun_x, warm, layer, above, and file. Only `seed` goes unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Lay a band of mist across the scene,' then immediately pins down the geometry (centred on row y, thickness rows deep). It is clearly distinguishable from decorative siblings like add_fire or add_glow without needing their schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is conveyed through evocative examples ('along a far shore, in a valley, over a marsh') rather than explicit when-to-use rules, and no alternative tool is named or excluded. An agent can infer the intended scenario but gets no guidance on choosing this over other atmosphere effects.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools